Marketing Analytics

I worked with a Greek statistician who would always try to correct my pronunciation of the Greek letter chi.  I would say “kai” and he would say something similar to “he”.  It was like he and key combined.  I can’t do it justice so I continued to say kai.

Regardless of how you pronounce it, the chi square test can be very useful.  In fact, one of my business school classes was spent discussing the uses and assumptions of the chi square test.  I won’t try to summarize a semester’s worth of material into a blog post.  Rather, I wanted to point out that chi square tests are used for categorical data and the only “gotcha” is that you have to use the actual counts (rather than percentages).  It is sensitive to cell counts and requires that there be at least 5 observations per cell.

The chi square test is a powerful statistical tool as it can tell you if there are significant differences between categories and it is the foundation for CHAID.  CHAID is an abbreviation for CHi-square Automated Interaction Detector.  It is one of the many segmentation techniques used in marketing and, if you plot out the tree that results from CHAID, it is a wonderfully visual way to see differences within your customers and/or prospects.  For CHAID you will need to define a dependent variable and undergo EDA (exploratory data analysis) similar to a modeling project.

A colleague and I had a very interesting discussion today over lunch.  I was arguing for the importance of industry in guiding the type of business questions you ask and hence the type of analyses you perform.  He believes that industry or vertical does not matter. 

My professional experience tells me otherwise.  Currently two of my clients have very different challenges.  One is a retailer trying to drive a repeat visit among its customer base.   Given the volume of customers they have and the average basket size, increasing the number of repeat visits can greatly impact revenue.  The other client is a software maker that sells to large manufacturers.  Identifying the right customer who would be interested in their product is key.  They have a much higher price point and much longer buying cycle than the retailer.  For them, understanding lead generation and lead conversion is vital in order to make their sales process more efficient.

However, there was on thing we could agree upon.  It all comes down to giving the right person the right message at the right time.

Earlier this week I heard on Marketplace that the banner ad started 15 years ago.  On October 27, 1994 the web site Hotwired.com posted banner ads for Volvo, MCI, Club Med and 1-800-Collect. The click rate was 78%!   Those were the days.

In 2007, BusinessWeek reported that the average click rate on a banner ad was 0.2% according to Eyeblaster , a New York-based online ad firm.  According to Advertising Age, the click rate for display ads has dropped 50% in less than two years.

One of my clients is focused heavily on e-mailing his customers.  However, it is only part of the equation.  Consumers are increasingly online 24 hours a day, 7 days a week.  Yes, they are still checking e-mails but they are also on Facebook, Twitter and blogs. 

It used to be that the question was direct mail or e-mail?  Now the question is not what channel to use but rather which channels to leverage.  The direct marketing strategy needs to consider traditional direct channels, such as e-mail and direct mail, as well as social networking sites.  The need for integration of branding and messaging has become even more important as consumers have a multitude of ways to learn about your company and its products and services. 

The other challenge with the plethora of channels that have evolved is that consumers are bombarded with information.  Some are abandoning their e-mail accounts because they are overwhelmed by their inboxes.  Others ignore their inboxes in favor of communication channels they control.  I don’t bother sending my sister e-mails anymore because they disappear into the black hole that is her inbox.  However, she will respond instantaneously to a text message and will e-mail me on occasion, when it is the best channel for her to communicate with me.   

As marketers, we need to go where our customers are and offer them relevant and honest information.

I was preparing for a meeting with a software company and found myself analyzing their industry using Porter’s five forces.  This is a framework for understanding the dynamics within an industry.  Also, the rigor of analyzing an industry makes you stop and first define the industry.  It sounds simple but can often be complex.  If there are multiple audiences or multiple products, you might want to do the analysis on each.  Next, it requires that you consider vendors, customers, and competitors.  In my first semester at business school, I must have done this exercise at least once a week. 

Years later I could not believe that I was still using this framework but I found it useful in preparing for my meetings.   One of the questions in the software business is who owns the customer?  If the software is sold via a value added reseller (VAR), then they may own the relationship.  Knowledge is power and the VARs may have all the power.  The VAR may know when the customer is likely to want an upgrade, add new seats or licenses, or purchase additional software for related business processes. 

If you are starting to work on a new industry or a new project, consider using the Porter five forces framework.  It can help you get to the heart of the strategic challenges within an industry.

I have been playing around with Google Analytics, trying to answer the question “What should my Mother make?”  For her birthday, I created an Etsy website so that she could sell her handcrafted jewelry online.  She had been selling bracelets, earrings, necklaces and lanyards at fairs and events. 

Well, she has been making bracelets like crazy.  She has 40 or so on her website and at least that many which have not yet made it online.  She has only a handful of necklaces currently available on the web and probably less than two dozen which could be posted to her website.  Should my Mother be making so many bracelets?  

I analyzed this from two different angles.  First, I analyzed what pages visitors were viewing on her site.  With Google Analytics you can set an entrance path and see what pages were viewed next.  I choose her home page to be the entrance path and found that:  

• 36% went to the second page of her shop
• 15% looked a her featured jewelry
• 13% clicked on the necklace section of her shop
• 8% visited the bracelet section of her shop

Google Analytics also tells you where visitors went next so I know if they continued browsing her inventory, looked at her profile page, or reviewed the feedback purchasers provided about her.  In addition to understanding how visitors are navigating the site, it also indicates what items are most popular.  For example, one jewelry item had many page views.

Visitors clicked on the necklace section more often than the bracelet section, which indicates that necklaces are more popular.  However, necklaces are the first section listed and it may be that the order is causing more page views.  Thus, I will switch the order and check back to see if the pattern continues. 

Next I analyzed her online sales.  Necklace sales outpace her bracelet sales.  In addition, the average cost of a necklace was more than twice the average cost of a bracelet.  I had thought that visitors would gravitate towards bracelets because they are less expensive; however, her online sales suggest that visitors are more likely to purchase necklaces even though they cost more.

From a business perspective, it makes sense for my Mother to make more necklaces; however, my analysis doesn’t take into account her offline sales or her artistic goals.  My Mother is an artist and not a factory.  However, I will suggest that we update her necklace inventory on the website.

For my Mother’s birthday, I created her very own website on www.etsy.com.  My Mom was speechless when she saw a site dedicated to selling her handcrafted jewelry online. 

This was a labor of love.  I spent many afternoons taking pictures of her necklaces, earrings, bracelets and lanyards and then researching the materials she used.  Using the etsy template, I created her “shop” by loading the pictures of her inventory, creating descriptions for each piece, setting up tags, outlining her shop’s terms and conditions (including shipping costs) and setting up a Google Analytics account so that I could track the performance of the website.   

It is so rewarding to receive feedback from customers that they love my Mother’s jewelry and think it is well made.  I also enjoy analyzing the web site’s performance and playing with Google Analytics.   In case you haven’t had a chance to use Google Analytics, here’s a screen shot from one of the standard Google Analytics’ reports.

The top graph shows the number of visits by day for the most recent month.  You can look at the metrics by day, week or month and set the time period to be analyzed.

Next on the report is site usage metrics including visits, pageviews, pages/visit, bounce rate, average time on the site, and percent new visits.  Most of these metrics are straight forward but you do need to be mindful of anomalies.  There are some weeks when I will see a huge spike in visits; however, those correspond to times when I was loading jewelry to the site and thus frequently visiting the site to see how it looked.

Her bounce rate is 39%.  Google Analytics defines it as follows, “bounce rate is the percentage of single-page visits or visits in which the person left your site from the entrance (landing) page.”  Not everyone who comes to her page will be interested in her jewelry.  Three visitors who typed in the keywords “buddha inspired chinese” were directed to her website.  I doubt they found what they were looking for!  Bounce rate is a powerful metric and I will be discussing it in another blog post.

Next is the visitor overview.  This is the number of new and existing visitors that came to the site.  It looks very similar to the Dashboard chart but the difference is that it measures visitors and not visits.  The Map Overlay World shows me at a quick glance where visitors to the site are coming from in the world. 

The pie chart below shows the traffic sources — direct traffic, search engines and referring sites.  Finally, the report shows an over view of the pages that had the most pageviews.  The first is the home page of her site and the subsequent ones are the pages for particular jewelry.

 I have no idea what I will do for my Mother’s next birthday but I will probably still be playing with Google Analytics until then.

Continuing on the theme of segmentation, RFM Analysis is another tool for understanding and identifying different types of customers.  RFM stands for recency, frequency and monetary value.  This tool will help you:

1. understand customer value quickly when limited data are available (e.g., just purchase data)
2. develop a basic value segmentation that can be used to determine if your customer strategy is optimal
3. find untapped markets if there are segments which are not targeted
4. gain insight into gaps that might exist between accepted wisdom about the customer base and actual purchase behavior

The name suggests that recency is the most important factor for determining a customer’s value followed by frequency and monetary value.  However, you can set different priorities.  For one of my clients, monetary value was more important than recency and frequency.  Thus, their analysis was driven by monetary value first, recency and finally frequency.  It all depends on your product and the typical buying cycle.

The actual analysis involves calculating the R, F, and M dimensions, specifically:

1. creating a reasonable number of categories based on the date of most recent purchase (e.g., date was within the last month, within most recent 2 to 6 months, within prior 7 to 12 months, etc.)
2. breaking the number of purchases into a reasonable number of categories similar to recency
3. summing all revenue and creating a reasonable number of categories similar to recency

The number of categories you create depends on how you intend to implement the RFM analysis and should be guided by the means and standard deviations of the variables.

The fun part comes when you bring all of this together.  You first need to decide which dimension is most important and which is the least important.  Next, you need to determine the number of segments you want.  Will it be high, medium and low or 1 through 10?  If there are too few segments, then the segmentation will not be very targeted.  If there are too many segments, it may become a burden to implement and may ultimately be considered too complicated to use.  Business judgement and knowledge of the customers’ behavior should drive the creation of the segments. 

Once the segments have been decided, business rules or code can be written so that the segments are applied to your customer base on a regular basis.  This has the advantage of identifying new best customers or up and comers that can then be targeted with a special welcome communication.    Further, the segmentation can be used with other tools to drive marketing messages and campaigns.  However, you may need to revisit your RFM segments from time to time as your business changes significantly.   For example, if you raise or lower prices significantly after the segments are put into production, you will want to reassess the original recency categories.

Cluster segmentation is a descriptive, multivariate technique that creates distinct, homogeneous groups within your customer base.  The goal of cluster segmentation is to classify consumers or businesses based on behaviors, demographics or firmographics, and/or attitudes.  In this way, you can develop more targeted programs and tailor messages based on the needs and characteristics of specific groups.  One client reorganized their marketing department as a result of a segmentation project I worked on, assigning one marketer to each segment so that consistent messaging and product offers could be employed against each customer group.  Further,the segments that are developed can be combined with models or other segmentation schemes to identify the best customers to target for particular campaign or offer. 

Determining what methodology to use for clustering depends on many factors including your clustering software, the type of data you have, and the number of consumers or businesses available for segmentation.  You should also consider the optimal number of segments to meet the business objective and which behaviors or other factors are most important in defining customers.    

Regardless the methodology chosen, you will need to do data prep.  You typically start with data summarized to the household level for B2C analysis and establishment or enterprise level for B2B analysis.  You might also need to do missing value substitution, transform categorical variables to binary or scaled variables, weight variables to drive preferred ones into the solution,  and standardize continuous variables.

Data reduction might also be necessary if you have many variables.  Tools for data reduction include correlation analysis, principal components and factor analysis.  

Once that is complete, you can create your segmentation schemes.  I run many more segmentation solutions than I show to a client because I want segments that are actionable within the client’s marketing plans and that are intuitive as well as not overly complicated.  In addition, I test the validity of my cluster solutions through goodness of fit statistical measurements and by replicating my results on a hold-out sample.   The end result is that a company can align its marketing efforts against segments, taking a customer-centered approach rather than treating every customer the same.  Cluster segmentation can be a tool for giving the right message at the right time to the right person.

My clients often know who their best customers are.  Typically the best are the top 20% of customers that generate 80% of the profits.  These are the customers you most want to retain.  The question becomes who are the customers that you should try to migrate into your best customer segment?  Figuring out who are the next best requires research into their behaviors, demographics or firmographics, and attitudes. 

 Segmentation is one way to separate your customer base into differentiated groups against which relevant marketing communicationsand strategies can be developed and executed.  There are many different types of segmentation and techniques including cluster analysis, RFM and CHAID.

Regardless of what method you choose, bear in mind that a good segmentation scheme is often a result of art and science.  Segments should make sense intuitively and, if they are data driven, should be sound statistically.  In my next post I will describe clustering and how that is used for segmentation.